extract audio from mp4 movie and save as mp3 (using ffmpeg)

extractAudioFromMp4.py

#!/usr/bin/python
# batch conversion: extract audio from all mp4's in sourceFolder and its subfolders and save as mp3.
# e.g. python extractAudioFromMp4.py sourceFolder destinationFolder

import sys
import os
from glob import glob
from subprocess import call
import shlex

def main(argv):
	if len(argv) < 2:
		print "missing arguments (arg1: source folder path, arg2: destination folder path)"
		exit(1)

	#parse arguments
	sourceFolder = argv[0]
	destinationFolder = argv[1]

	# if os.listdir(destinationFolder):
	# 	print "files exist in destination, exit."
	# 	exit(1)
	
	#get all filepaths
	filePaths = [y for x in os.walk(sourceFolder) for y in glob(os.path.join(x[0], '*.mp4'))]
	if len(filePaths) == 0:
		print "no files were found, exiting."
		exit(1)
	else:
		print "number of files to convert: " + str(len(filePaths))

	#file names
	filenames = []
	for filepath in filePaths:
		filenames.append(os.path.basename(filepath))

	#search for duplicates
	duplicates = listDuplicates(filenames)
	if len(duplicates) > 0:
		print "early exit because duplicate files were found: " + str(duplicates)
		exit(1)

	#start conversion
	for filepath in filePaths:
		destinationFilename = os.path.splitext(os.path.basename(filepath))[0]
		destinationFilepath = os.path.join(destinationFolder, destinationFilename)
		command = "ffmpeg -i " + "'" + filepath + "'" + " -ab 192k " + "'" + destinationFilepath + ".mp3" + "'"
		
		args = shlex.split(command)
		call(args)
		# call(["ffmpeg", "-i", '""' + filepath + '""', "-codec:a libmp3lame", "-qscale:a 320k", '""' + destinationFilepath + '""'])


def listDuplicates(seq):
  	seen = set()
  	seen_add = seen.add

  	# adds all elements it doesn't know yet to seen and all other to seen_twice
  	seen_twice = set( x for x in seq if x in seen or seen_add(x) )
  	# turn the set into a list (as requested)
  	return list( seen_twice )

if __name__ == "__main__":
	main(sys.argv[1:])